Campaign B v2 (InfoNCE mix) both seeds PASS; retro-erank corrected after overwrite catch (HF copies were the true v1): spread v1 180 > v2 139 (baseline 239) — target granularity governs spread, not loss family
Campaign B v2 (InfoNCE mix) both seeds PASS; retro-erank corrected after overwrite catch (HF copies were the true v1): spread v1 180 > v2 139 (baseline 239) — target granularity governs spread, not loss family
Campaign B v2 (InfoNCE mix) both seeds PASS; retro-erank corrected after overwrite catch (HF copies were the true v1): spread v1 180 > v2 139 (baseline 239) — target granularity governs spread, not loss family
Campaign B v2 (InfoNCE mix) both seeds PASS; retro-erank corrected after overwrite catch (HF copies were the true v1): spread v1 180 > v2 139 (baseline 239) — target granularity governs spread, not loss family
Campaign B v1 PASSED both seeds: two-teacher alloy into mini-beatrix arm — meet +0.22/+0.21, preservation IMPROVED (B9 digit 0.837->0.971), LM +2pts, bit-exact off
Campaign B v1 PASSED both seeds: two-teacher alloy into mini-beatrix arm — meet +0.22/+0.21, preservation IMPROVED (B9 digit 0.837->0.971), LM +2pts, bit-exact off
Campaign B v1 PASSED both seeds: two-teacher alloy into mini-beatrix arm — meet +0.22/+0.21, preservation IMPROVED (B9 digit 0.837->0.971), LM +2pts, bit-exact off
Campaign B v1 PASSED both seeds: two-teacher alloy into mini-beatrix arm — meet +0.22/+0.21, preservation IMPROVED (B9 digit 0.837->0.971), LM +2pts, bit-exact off
Campaign B v1 PASSED both seeds: two-teacher alloy into mini-beatrix arm — meet +0.22/+0.21, preservation IMPROVED (B9 digit 0.837->0.971), LM +2pts, bit-exact off
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
frame prototype v0.1: byte-state arm beats index twin (digits 0.275 vs 0.045, twin has only 200 keys for 999 states); RSA says the codebook kept C ancestry; entry channel real vs failing random control
single-tokenizer walk of C: 999 states, zero UNK, 95.4% mass whole; digit grammar = longest-prefix+trailing-digit; only liters/Subtract compose non-trivially
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
mapwise state representations: byte language C built from codex, both vocabs projected through it (full row contract); joint content-state map + words-of-C table
byte-specific state gauge: A 82449 / B 63001 trie states, 28246 co-occupied; 12.0K/12.5K whole states walk fully on shared structure vs 10801 exact name matches
